Domain Adaptive Faster R-CNN for Object Detection in the Wild 論文紹介Tsukasa Takagi
Domain Adaptive Faster R-CNN for Object Detection in the Wild
第46回 コンピュータビジョン勉強会@関東 CVPR2018読み会(前編)にて発表したスライドです。
https://kantocv.connpass.com/event/88613/
Domain Adaptive Faster R-CNN for Object Detection in the Wild 論文紹介Tsukasa Takagi
Domain Adaptive Faster R-CNN for Object Detection in the Wild
第46回 コンピュータビジョン勉強会@関東 CVPR2018読み会(前編)にて発表したスライドです。
https://kantocv.connpass.com/event/88613/
The document describes ABEJA's platform for faster circulation of high-volume data through its processes of data collection, storage, training, deploying models for inferring and retraining using the collected data. The platform allows for building and deploying machine learning models at scale for applications that require processing large amounts of data.
This document contains a list of 20 links to GitHub repositories related to machine learning and computer vision. The repositories contain resources for tasks such as object detection, image generation, semantic segmentation, depth estimation, graph neural networks, and social behavior analysis. A variety of approaches are represented, including convolutional neural networks, generative adversarial networks, graph convolutional networks, and reinforcement learning models.